基于同态加密的前馈神经网络隐私保护方案  

Privacy Protection Scheme of Feedforward Neural Network Based on Homomorphic Encryption

作　　者：林湛航 向广利[1] 李祯鹏 徐子怡 LIN Zhanhang;XIANG Guangli;LI Zhenpeng;XU Ziyi(School of Computer and Artificial Intelligence,Wuhan University of Technology,Wuhan 430070,China)

机构地区：[1]武汉理工大学计算机与人工智能学院,武汉430070

出　　处：《信息网络安全》2024年第9期1375-1385,共11页Netinfo Security

基　　金：国家自然科学基金[62276196]。

摘　　要：当前的隐私保护机器学习方法在保障数据隐私方面取得了一定进展,然而在计算效率和服务器资源利用等方面仍存在挑战。为了充分利用服务器资源,针对前馈神经网络,文章提出一种基于主从服务器架构的同态加密前馈神经网络隐私保护方案。该方案通过秘密共享技术将数据和模型参数分发至两个不共谋的服务器,并利用同态加密技术对服务器间的交互信息进行加密。在计算效率方面,通过避免耗时的密文向量和明文矩阵乘法,缩短了方案的运行时间。在安全性方面,通过引入随机噪声对秘密份额加噪,防止了服务器获得原始数据信息。实验结果表明,文章所提方案在计算复杂度和通信开销上均有显著改善。The current privacy-preserving machine learning(PPML)method has made certain progress in ensuring data privacy,but it still faces challenges in terms of computing efficiency and server resource utilization.In order to make full use of server resources and for feedforward neural network,this paper proposed a privacy protection scheme for homomorphic encryption feedforward neural network based on a master-slave server architecture.This scheme used secret sharing technology to distribute data and model parameters to two non-colluding servers,and used homomorphic encryption technology to encrypt interactive information between servers.In terms of computational efficiency,the running time of the scheme was reduced by avoiding running ciphertext management and plaintext matrix multiplication.In terms of security,adding noise to secret sharing by introducing random noise prevents the server from obtaining original data information.The experimental results show that the proposed scheme has improved both in computational complexity and communication overhead.

关 键 词：同态加密 神经网络 隐私保护 秘密共享 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]